Workflow for creating, testing, enabling, promoting, and removing Custom Tools from a code folder.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow reads external GitHub repositories specified by the user or via URLs, which can contain untrusted code and README text processed during the custom tool scan.
siddsachar/row-bot
2327c6c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.